FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283722433> ?p ?o ?g. }

• W4283722433 endingPage "109221" @default.
• W4283722433 startingPage "109221" @default.
• W4283722433 abstract "Prediction of reference evapotranspiration (ET0) remains a challenge, especially with forward multi-step forecasting. The bottleneck facing current research is the limitation of the span of the forecasting time horizons, which can be rather disappointing, especially when long-term forecasting is desired. In this study, an explainable model structure, represented by a one-dimensional convolutional neural network (CNN-1D) was compared to the long short-term memory network (LSTM) and gated recurrent unit network (GRU), both formulated with black-box model method. The comparison included the application of different forecasting strategies (iterated vs. multiple-input–multiple-output (MIMO)) and approaches (direct vs. indirect). This study was conducted at four stations scattered across the Peninsular Malaysia. From the results of this study, the explainable CNN-1D model generally performed poorer than its black-box counterparts at most of the stations. The type of model and its structure, forecasting strategy and approach formed a complex relationship to indicate that there is no one-for-all solution in the case of the long-term prediction of monthly mean ET0. Despite that, the GRU-based models stood out as the most well-suited option for the task, with the MIMO forecasting strategy being favoured over the iterated strategy. At the four stations, the average mean absolute error (MAE), root mean square error (RMSE), mean percentage error (MAPE) and the Kling–Gupta efficiency (KGE) of the best GRU models were 0.182 mm/day, 0.260 mm/day, 4.972 % and 0.747, respectively. It was found that the prediction residual of the best GRU models did not possess a clear trend as the forecasting horizon was lengthened. The results implied that theoretically, the forecasting time horizon could be extended over to a longer temporal scale without any deterioration in the model performance. This finding is positive as it brings about the possibility of allocating the water budget with higher confidence. Nevertheless, the LSTM and GRU models developed in this study, were believed to have more tremendous potential if they were to be designed with purpose (such as the integration of optimisation algorithm), instead of being a mere black-box structure." @default.
• W4283722433 created "2022-07-01" @default.
• W4283722433 creator A5006424822 @default.
• W4283722433 creator A5010789167 @default.
• W4283722433 creator A5013453921 @default.
• W4283722433 creator A5051234103 @default.
• W4283722433 creator A5051717915 @default.
• W4283722433 creator A5069455833 @default.
• W4283722433 date "2022-09-01" @default.
• W4283722433 modified "2023-10-17" @default.
• W4283722433 title "Long-term forecasting of monthly mean reference evapotranspiration using deep neural network: A comparison of training strategies and approaches" @default.
• W4283722433 cites W1920055338 @default.
• W4283722433 cites W2003706483 @default.
• W4283722433 cites W2014928429 @default.
• W4283722433 cites W2037855854 @default.
• W4283722433 cites W2064675550 @default.
• W4283722433 cites W2296778215 @default.
• W4283722433 cites W2336157727 @default.
• W4283722433 cites W2921467030 @default.
• W4283722433 cites W2961472717 @default.
• W4283722433 cites W2979474917 @default.
• W4283722433 cites W2989584745 @default.
• W4283722433 cites W2998895100 @default.
• W4283722433 cites W3010047009 @default.
• W4283722433 cites W3014274309 @default.
• W4283722433 cites W3016890397 @default.
• W4283722433 cites W3021357433 @default.
• W4283722433 cites W3036299832 @default.
• W4283722433 cites W3038024393 @default.
• W4283722433 cites W3043392635 @default.
• W4283722433 cites W3045832151 @default.
• W4283722433 cites W3046457451 @default.
• W4283722433 cites W3081241543 @default.
• W4283722433 cites W3081335492 @default.
• W4283722433 cites W3112756409 @default.
• W4283722433 cites W3123900242 @default.
• W4283722433 cites W3131536296 @default.
• W4283722433 cites W3168760778 @default.
• W4283722433 cites W3173235060 @default.
• W4283722433 cites W3214759127 @default.
• W4283722433 cites W3217470649 @default.
• W4283722433 cites W332085899 @default.
• W4283722433 doi "https://doi.org/10.1016/j.asoc.2022.109221" @default.
• W4283722433 hasPublicationYear "2022" @default.
• W4283722433 type Work @default.
• W4283722433 citedByCount "13" @default.
• W4283722433 countsByYear W42837224332022 @default.
• W4283722433 countsByYear W42837224332023 @default.
• W4283722433 crossrefType "journal-article" @default.
• W4283722433 hasAuthorship W4283722433A5006424822 @default.
• W4283722433 hasAuthorship W4283722433A5010789167 @default.
• W4283722433 hasAuthorship W4283722433A5013453921 @default.
• W4283722433 hasAuthorship W4283722433A5051234103 @default.
• W4283722433 hasAuthorship W4283722433A5051717915 @default.
• W4283722433 hasAuthorship W4283722433A5069455833 @default.
• W4283722433 hasConcept C105795698 @default.
• W4283722433 hasConcept C11413529 @default.
• W4283722433 hasConcept C121332964 @default.
• W4283722433 hasConcept C139945424 @default.
• W4283722433 hasConcept C150217764 @default.
• W4283722433 hasConcept C154945302 @default.
• W4283722433 hasConcept C155512373 @default.
• W4283722433 hasConcept C176783924 @default.
• W4283722433 hasConcept C18903297 @default.
• W4283722433 hasConcept C33923547 @default.
• W4283722433 hasConcept C41008148 @default.
• W4283722433 hasConcept C50644808 @default.
• W4283722433 hasConcept C61797465 @default.
• W4283722433 hasConcept C62520636 @default.
• W4283722433 hasConcept C81363708 @default.
• W4283722433 hasConcept C86803240 @default.
• W4283722433 hasConceptScore W4283722433C105795698 @default.
• W4283722433 hasConceptScore W4283722433C11413529 @default.
• W4283722433 hasConceptScore W4283722433C121332964 @default.
• W4283722433 hasConceptScore W4283722433C139945424 @default.
• W4283722433 hasConceptScore W4283722433C150217764 @default.
• W4283722433 hasConceptScore W4283722433C154945302 @default.
• W4283722433 hasConceptScore W4283722433C155512373 @default.
• W4283722433 hasConceptScore W4283722433C176783924 @default.
• W4283722433 hasConceptScore W4283722433C18903297 @default.
• W4283722433 hasConceptScore W4283722433C33923547 @default.
• W4283722433 hasConceptScore W4283722433C41008148 @default.
• W4283722433 hasConceptScore W4283722433C50644808 @default.
• W4283722433 hasConceptScore W4283722433C61797465 @default.
• W4283722433 hasConceptScore W4283722433C62520636 @default.
• W4283722433 hasConceptScore W4283722433C81363708 @default.
• W4283722433 hasConceptScore W4283722433C86803240 @default.
• W4283722433 hasLocation W42837224331 @default.
• W4283722433 hasOpenAccess W4283722433 @default.
• W4283722433 hasPrimaryLocation W42837224331 @default.
• W4283722433 hasRelatedWork W2039947585 @default.
• W4283722433 hasRelatedWork W308010854 @default.
• W4283722433 hasRelatedWork W3111532652 @default.
• W4283722433 hasRelatedWork W3178576217 @default.
• W4283722433 hasRelatedWork W4210644201 @default.
• W4283722433 hasRelatedWork W4283367183 @default.
• W4283722433 hasRelatedWork W4285102093 @default.
• W4283722433 hasRelatedWork W4318676890 @default.

• next